Technique for skew detection of printed arabic documents
AssigneesKing Fahd University of Petroleum and Minerals, King Abdulaziz City for Science and Technology
InventorIrfan Ahmad
Life of this patent
Estimating the term…
Abstract
A digital document skew detection and correction system that uses horizontal pixel projection analysis to detect the prominent writing line of Arabic text. The system removes both small and large components and divides the document into segments. The system uses the pixel projection results at varying angles to pinpoint the highest horizontal pixel concentration corresponding to the writing line of the Arabic text to determine the skew angle for each divided document segment. The skew angle variable is averaged between the documents segments before being reattached; a user notification application is activated if the differences between skewed angles exceed a threshold. The original document is rotated in the opposite direction of the estimated skew angle to correct the skew.
Claims13
A document skew detection method, comprising:
- binarizing, with circuitry, a document to provide a binarized document image,
- performing, by the circuitry, a connected component analysis to remove noise and non-text elements from the binarized document image;
- then
- splitting, by the circuitry, the binarized document image into a first image and a second image;
- individually estimating, by the circuitry, a coarse skew angle for the first image and second image by performing a first pixel projection to determine a coarse horizontal line based on a maximum concentration of pixels in the pixel projection of a sharp writing line of script of the first image of the binarized document and the second image of the binarized document image;
- individually estimating, by the circuitry, a fine skew angle within the coarse skew angle for the first image and second image by performing a second pixel projection to determine a fine horizontal line based on a maximum concentration of pixels in the pixel projection of the sharp writing line of script of the first image of the binarized document and the second image of the binarized document;
- and
- averaging, by the circuitry, the fine skew angle for the first image and the second image to determine a final skew angle.
Dependencies are inferred from the claim text.